List TouchDesigner operators

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false, covering safety. The description adds useful context about operating on COMP children and supports recursion/filtering, which aligns with parameters. However, it does not disclose return format, pagination, or limit behavior, so it adds only moderate transparency beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that leads with the primary action, then adds optional modifiers. Every phrase conveys key information without redundancy, making it highly scannable for an agent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given there is no output schema, the description does not mention what the tool returns (e.g., list of paths, names, or dicts). It also omits edge cases like depth limits or limit defaults. While the safety annotations cover the read-only aspect, a lightly parameterized introspection tool like this would benefit from a sentence describing return value or list format.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 20% (only 'parent' has a description), so the description must compensate. It does explain the roles of depth (recursive), family (filter by family), and pattern (name pattern), and implies parent is a COMP. But it does not explain the 'limit' parameter at all, and it leaves the exact meaning of 'children' (immediate vs recursive) to the depth parameter. This is partial compensation, not full.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('List') and resource ('children under a COMP'), and clarifies optional behavior (recursive, filtered by family or name pattern). This clearly distinguishes it from sibling tools like td_inspect_operator or td_sample_chop, which have different purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly implies when to use it: when you need to enumerate children of a COMP with optional filtering. It does not explicitly mention alternatives or exclusions, but the sibling tools are all sufficiently distinct in action that no warning is needed. It provides clear context without explicit when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.